日志
格式化Hive语法树(python)
为了容易看一点，把用explain得到的语法树加上一些缩进.
该代码只是简单的加上缩进.
效果
这是查询explain select key from kv mykv join test mytest on (mykv.key == mytest.id);语句获取的语法树
(TOK_QUERY
(TOK_FROM
(TOK_JOIN
(TOK_TABREF
(TOK_TABNAME kv)
mykv)
(TOK_TABREF
(TOK_TABNAME test)
mytest)
(==
(.
(TOK_TABLE_OR_COL mykv)
key)
(.
(TOK_TABLE_OR_COL mytest)
id)
)
)
)
(TOK_INSERT
(TOK_DESTINATION
(TOK_DIR TOK_TMP_FILE)
)
(TOK_SELECT
(TOK_SELEXPR
(TOK_TABLE_OR_COL key)
)
)
)
)
代码如下
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
Created on 2012-5-20
@author: fatkun
'''
import sys
# explain select key from kv mykv join test mytest on (mykv.key == mytest.id);
original_str = """(TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF
(TOK_TABNAME kv) mykv) (TOK_TABREF (TOK_TABNAME test) mytest)
(== (. (TOK_TABLE_OR_COL mykv) key) (. (TOK_TABLE_OR_COL mytest) id))))
(TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)))))"""
tmp_str = original_str.strip().replace('\n', '')
def my_print(mystr):
sys.stdout.write(mystr)
def print_indent(indent_level):
for i in range(indent_level):
my_print(' ' * 4)
indent_level = 0
for char in tmp_str:
if char == '(':
# 如果是左括号,先换行,然后打印缩进+(
my_print('\n')
print_indent(indent_level)
my_print(char)
indent_level += 1
elif char == ')':
# 如果是右括号,先打印),再换行,打印下一级别的缩进
indent_level -= 1
my_print(char)
my_print('\n')
print_indent(indent_level - 1)
else:
# 其他的直接打印出来
my_print(char)
/2 
